European RadiologyPub Date : 2025-10-01Epub Date: 2025-04-14DOI: 10.1007/s00330-025-11442-2
Lucas de Vries, M M Quirien Robbe, Ivo G H Jansen, S Mahsa Mojtahedi, Jan W Hoving, Susanne G H Olthuis, Robrecht R M M Knapen, Florentina M E Pinckaers, Manon Kappelhof, Ludo F M Beenen, Alida A Postma, Robert J van Oostenbrugge, Diederik W J Dippel, Efstratios Gavves, Bart J Emmer, Charles B L M Majoie, Wim H van Zwam, Henk A Marquering
{"title":"Automated collateral assessment restricted to the hypoperfused area for distal vessel occlusions in ischemic stroke.","authors":"Lucas de Vries, M M Quirien Robbe, Ivo G H Jansen, S Mahsa Mojtahedi, Jan W Hoving, Susanne G H Olthuis, Robrecht R M M Knapen, Florentina M E Pinckaers, Manon Kappelhof, Ludo F M Beenen, Alida A Postma, Robert J van Oostenbrugge, Diederik W J Dippel, Efstratios Gavves, Bart J Emmer, Charles B L M Majoie, Wim H van Zwam, Henk A Marquering","doi":"10.1007/s00330-025-11442-2","DOIUrl":"10.1007/s00330-025-11442-2","url":null,"abstract":"<p><strong>Objectives: </strong>This study aims to: (1) develop and evaluate a quantitative assessment of collateral status in the downstream area of an occluded intracranial artery in acute ischemic stroke and compare this method to middle cerebral artery (MCA)-based assessment; (2) determine the agreement between the automated occlusion-downstream area collateral score (ODACS) and expert raters' assessments, and compare this to inter-rater agreement.</p><p><strong>Methods: </strong>Patients from MR CLEAN-NO IV and MR CLEAN Registry with a proximal M1, distal M1, or M2 occlusion were included. Using the hypoperfused area from CT perfusion (CTP) as a proxy for the occlusion-downstream territory and automated vessel segmentations from CT angiography (CTA), ODACS is calculated as the vessel volume ratio between downstream ipsilateral and its contralateral regions. ODACS was compared to a whole MCA-territory approach and evaluated against visual scoring by two expert raters that visually estimated ODACS using CTA and CTP, and their inter-rater agreement.</p><p><strong>Results: </strong>The study included 204 patients with a proximal M1 (52%), distal M1 (32%), or M2 (16%) occlusion. ODACS yielded lower collateral scores than MCA-based scoring for all occlusion locations, with larger differences in more distal occlusions. For M2 occlusions, 58% of patients shifted from good (> 50%) to poor (≤ 50%) collateral filling of the occluded territory using ODACS. Moderate (weighted Cohen's kappa κ = 0.45) inter-rater agreement and fair (κ = 0.35) to moderate (κ = 0.51) ODACS-rater agreement were observed.</p><p><strong>Conclusions: </strong>ODACS yields lower collateral scores compared to MCA-based scoring and is comparable to scores from expert raters.</p><p><strong>Key points: </strong>Question CT angiography-based collateral assessment in the MCA territory is inadequate to assess the collateral status in patients with distal vessel occlusions. Findings Our automated ODACS revealed lower collateral scores than traditional whole-territory assessment, especially in distal vessel occlusions. Clinical relevance The more precise evaluation of affected brain territories through automated occlusion-downstream area assessments prevents an overestimation of collateral status in distal occlusions, which could lead to improved patient selection and treatment decisions in acute stroke care.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"6127-6139"},"PeriodicalIF":4.7,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143960505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
European RadiologyPub Date : 2025-10-01Epub Date: 2025-04-27DOI: 10.1007/s00330-025-11634-w
Emre Ünal, Ümran Esen, Aycan Uysal, Türkmen Turan Çiftçi, Devrim Akinci, Erkan Parlak
{"title":"Combined endoscopic-percutaneous approach for magnetic compression anastomosis in post-transplant anastomotic biliary strictures.","authors":"Emre Ünal, Ümran Esen, Aycan Uysal, Türkmen Turan Çiftçi, Devrim Akinci, Erkan Parlak","doi":"10.1007/s00330-025-11634-w","DOIUrl":"10.1007/s00330-025-11634-w","url":null,"abstract":"<p><strong>Objectives: </strong>To investigate long-term outcomes of combined endoscopic-percutaneous methods for endoscopically unmanageable anastomotic biliary strictures in living donor liver recipients.</p><p><strong>Materials and methods: </strong>This retrospective single-center study included 144 patients referred for biliary stricture between November 2017 and May 2023. Eighty-eight patients (leak = 8, non-anastomotic stricture = 3, treatment refused = 12, successful ERCP = 65) were excluded. Patients initially underwent percutaneous biliary drainage. Patients for whom percutaneous intervention was successful in traversing stricture were followed up with fully-covered self-expandable metallic stents and/or plastic catheter stents. However, in case of failure, magnetic compression anastomosis (MCA) was performed.</p><p><strong>Results: </strong>A total of 56 patients (mean age, 59 years ±11; 35 men) comprised the study group. Percutaneous intervention was successful in traversing the stricture in 26/56 patients. Among the remaining 30 patients, 26 were eligible for MCA, which was performed successfully in 24 patients (92%). The mean duration from magnet placement to internalization was 7.71 ± 2.77 days (95% CI: 6.54-8.88). Altogether, in 47 patients (24 of whom underwent MCA), percutaneous drains were removed following biliary stenting. The mean follow-up was 1082.5 ± 668.2 days (95% CI: 907.49-1257.51). In 19 patients (40%), recurrent stricture was evident at ERCP during a median follow-up of 90 (IQR: 60-210) days following stent removal. The recurrent stricture rate following MCA (n = 6/24) was significantly lower compared to patients in whom MCA was not performed (n = 13/23; p = 0.026). Overall, stent type had no significant effect on patency (p = 0.189).</p><p><strong>Conclusion: </strong>Percutaneous biliary procedures are essential for endoscopically unmanageable post-transplant anastomotic biliary strictures. MCA seems to provide higher patency rates even in patients with total biliary occlusion.</p><p><strong>Key points: </strong>Question What steps can be taken when endoscopy fails in the treatment of post-transplant anastomotic biliary strictures? Findings Percutaneous biliary access and magnetic compression anastomosis can be applied to increase graft survival in the setting of endoscopically unmanageable post-transplant biliary strictures. Clinical relevance Impassable biliary obstructions are unfortunate complications and not uncommon in liver transplant recipients. Magnetic compression anastomosis is an alternative minimally invasive method of treatment for complete biliary occlusions.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"6598-6607"},"PeriodicalIF":4.7,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12417223/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143991158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
European RadiologyPub Date : 2025-10-01Epub Date: 2025-04-19DOI: 10.1007/s00330-025-11588-z
Young Wook Lyoo, Haneol Lee, Junhyeok Lee, Jung Hyun Park, Inpyeong Hwang, Jin Wook Chung, Seung Hong Choi, Jaejun Yoo, Kyu Sung Choi
{"title":"Deep learning enhances reliability of dynamic contrast-enhanced MRI in diffuse gliomas: bypassing post-processing and providing uncertainty maps.","authors":"Young Wook Lyoo, Haneol Lee, Junhyeok Lee, Jung Hyun Park, Inpyeong Hwang, Jin Wook Chung, Seung Hong Choi, Jaejun Yoo, Kyu Sung Choi","doi":"10.1007/s00330-025-11588-z","DOIUrl":"10.1007/s00330-025-11588-z","url":null,"abstract":"<p><strong>Objectives: </strong>To propose and evaluate a novel deep learning model for directly estimating pharmacokinetic (PK) parameter maps and uncertainty estimation from DCE-MRI.</p><p><strong>Methods: </strong>In this single-center study, patients with adult-type diffuse gliomas who underwent preoperative DCE-MRI from Apr 2010 to Feb 2020 were retrospectively enrolled. A spatiotemporal probabilistic model was used to create synthetic PK maps. Structural Similarity Index Measure (SSIM) to ground truth (GT) maps were calculated. Reliability was evaluated using the intraclass correlation coefficient (ICC) for synthetic and GT PK maps. For clinical validation, Area Under the Receiver Operating Characteristic Curve (AUROC) was obtained for predicting WHO low vs high grade and IDH-wildtype vs mutant.</p><p><strong>Results: </strong>329 patients (mean age, 55 ± 15 years, 197 men) were eligible. Synthetic K<sup>trans</sup>, Vp, Ve maps showed high SSIM (0.961, 0.962, 0.890) compared to the GT maps. The ICC of PK maps was significantly higher in synthetic PK maps compared to the conventional approach: 1.00 vs 0.68 (p < 0.001) for K<sup>trans</sup>, 1.00 vs 0.59 (p < 0.001) for Vp, 1.00 vs 0.64 (p < 0.001) for Ve. PK values of enhancing tumor portion obtained from synthetic and GT maps were comparable in AUROC: (1) K<sup>trans</sup>, 0.857 vs 0.842 (p = 0.57); Vp, 0.864 vs 0.835 (p = 0.31); and Ve, 0.835 vs 0.830 (p = 0.88) for mutation prediction. (2) K<sup>trans</sup>, 0.934 vs 0.907 (p = 0.50); Vp, 0.927 vs 0.899 (p = 0.24); and Ve, 0.945 vs 0.910 (p = 0.24) for glioma grading.</p><p><strong>Conclusion: </strong>Synthetic PK maps generated from DCE-MRI using a spatiotemporal probabilistic deep-learning model showed improved reliability without compromising diagnostic performance in glioma grading.</p><p><strong>Key points: </strong>Question Can a deep learning model enhance the reliability of dynamic contrast-enhanced MRI (DCE-MRI) for more consistent and clinically acceptable glioma imaging? Findings A spatiotemporal deep learning model outperformed the Tofts model in Ktrans reliability and preserved diagnostic performance for IDH mutation and glioma grade, bypassing arterial input function estimation. Clinical relevance Enhancing DCE-MRI reliability with deep learning improves imaging consistency, supports molecular tumor characterization through reproducible pharmacokinetic maps, and enables personalized treatment planning, which might lead to better clinical outcomes for patients with diffuse gliomas.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"6229-6239"},"PeriodicalIF":4.7,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12417281/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143992581","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
European RadiologyPub Date : 2025-10-01Epub Date: 2025-04-15DOI: 10.1007/s00330-025-11580-7
Roberta Eufrasia Ledda, Gianluca Milanese, Marie-Pierre Revel, Annemiek Snoeckx
{"title":"Pros and cons of reporting incidental findings in lung cancer screening.","authors":"Roberta Eufrasia Ledda, Gianluca Milanese, Marie-Pierre Revel, Annemiek Snoeckx","doi":"10.1007/s00330-025-11580-7","DOIUrl":"10.1007/s00330-025-11580-7","url":null,"abstract":"<p><p>Incidental findings (IFs) are common in lung cancer screening (LCS). While the detection of some of these findings can lead to early diagnosis and treatment of clinically significant conditions, it also carries the risks of overdiagnosis and overtreatment, causing anxiety for patients and increased economic costs for health systems. Effective management of IFs requires a balanced approach guided by clear guidelines, standardized reporting, and participants-centered communication. As the field of LCS evolves, continued research and innovation will be essential in refining the strategies for managing IFs, ensuring that the benefits of screening are maximized while minimizing potential harm. Evidence-based guidelines on reporting and management of IFs, however, are still lacking. This narrative review explores the pros and cons of reporting IFs in LCS, focusing on key controversies. KEY POINTS: Reporting and managing incidental findings in lung cancer screening is largely debated. The detection of incidental findings can lead to early diagnosis of clinically significant conditions but carries the risks of overdiagnosis and overtreatment. A balance must be found to have a positive impact on the population while not placing a burden on healthcare systems.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"6350-6356"},"PeriodicalIF":4.7,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12417295/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143995096","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
European RadiologyPub Date : 2025-10-01Epub Date: 2025-04-11DOI: 10.1007/s00330-025-11543-y
Xinshu Zhao, Jianan Xue, Weiying Yu, Rong Dong, Shuqi Liu, Peiwen Wang, Jingyao Wang, Feng Guo, Deng-Ke Teng
{"title":"The long-term effects of thermal ablation for benign thyroid nodules: a systematic review and meta-analysis.","authors":"Xinshu Zhao, Jianan Xue, Weiying Yu, Rong Dong, Shuqi Liu, Peiwen Wang, Jingyao Wang, Feng Guo, Deng-Ke Teng","doi":"10.1007/s00330-025-11543-y","DOIUrl":"10.1007/s00330-025-11543-y","url":null,"abstract":"<p><strong>Background: </strong>Ultrasound-guided thermal ablation has become an option for treating benign thyroid nodules. To evaluate the long-term safety and efficacy of thermal ablation for benign thyroid nodules (BTNs), cases involving 3 years of follow-up were studied via a systematic review and meta-analysis.</p><p><strong>Methods: </strong>Studies published up to January 2024 were searched in the MEDLINE, Embase, and Cochrane Library databases; these studies included 3 years of follow-up data on patients with BTNs who underwent thermal ablation therapy. The reduction in the mean nodule volume, volume reduction rate (VRR), rate of regrowth during follow-up, compression symptoms, postoperative cosmetic effects, and ablation complications during follow-up were analyzed over 3 years. In a subgroup analysis, laser ablation (LA), radiofrequency ablation (RFA), and microwave ablation (MWA) were compared.</p><p><strong>Results: </strong>After 3 years of follow-up, the volumes of BTNs decreased significantly after thermal ablation (p < 0.00001). The VRR was 71.59%. The regrowth rate was 7.41%. The major complication rate was 1.96%. The symptom scores and cosmetic scores significantly decreased (p < 0.00001). According to our subgroup analysis, the combined VRR was 53.27% in the LA group, 79.51% in the RFA group and 89.68% in the MWA group. The regrowth rate in the MWA-treated patients was lower (1.96%) than that in the other groups. Although the rate of the major complication was slightly greater (1.96%), there were no statistically significant differences compared with those in the LA and RFA groups.</p><p><strong>Conclusion: </strong>Long-term follow-up analysis indicated that thermal ablation is a safe and effective method for treating benign thyroid nodules. In addition, compared with RFA and LA, MWA may be more effective at treating benign thyroid nodules.</p><p><strong>Key points: </strong>Question What is the long-term outcome of thermal ablation in the treatment of benign thyroid nodules? Findings Thermal ablation is safe and effective for benign thyroid nodules. Clinical relevance Laser ablation, radiofrequency ablation, and microwave ablation showed no difference in safety, but microwave ablation may be more effective in treating benign thyroid nodules.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"6089-6100"},"PeriodicalIF":4.7,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143963381","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
European RadiologyPub Date : 2025-10-01Epub Date: 2025-04-26DOI: 10.1007/s00330-025-11617-x
Yujeong Eo, Jong-Tae Yoon, Byung Jun Kim, Deok Hee Lee, Yun Hwa Roh, Hye Hyeon Moon, Pae Sun Suh, Jae-Chan Ryu, Boseong Kwon, Yunsun Song
{"title":"Effectiveness of wedge filter application in reducing lens radiation dose during diagnostic cerebral angiography: a phantom and prospective study.","authors":"Yujeong Eo, Jong-Tae Yoon, Byung Jun Kim, Deok Hee Lee, Yun Hwa Roh, Hye Hyeon Moon, Pae Sun Suh, Jae-Chan Ryu, Boseong Kwon, Yunsun Song","doi":"10.1007/s00330-025-11617-x","DOIUrl":"10.1007/s00330-025-11617-x","url":null,"abstract":"<p><strong>Objective: </strong>Diagnostic cerebral angiography poses a risk of direct radiation exposure to the eye lens. This study aimed to evaluate the effectiveness of using a wedge filter to reduce lens exposure during examination.</p><p><strong>Methods: </strong>A phantom study was initially conducted to evaluate the efficacy and determine the optimal depth of the wedge filter. Twenty patients with intracranial aneurysms scheduled for diagnostic cerebral angiography were prospectively enrolled. For each patient, the lens dose reduction protocol (involving a wedge filter) was used on one internal carotid artery (ICA), whereas the standard protocol was applied to the other ICA. Photoluminescent glass dosimeters were used to measure the lens dose. Quantitative noise measurements and qualitative analysis were performed to assess image quality.</p><p><strong>Results: </strong>The phantom study demonstrated that the wedge filter reduced the radiation dose to the eye lens in anteroposterior (25.5% reduction at 4 cm depth) and lateral projections (28.8% reduction at 3 cm depth). In the patient study (20 patients, 60% female, mean age 57.5 years), the lens dose reduction protocol reduced the dose by 47.2% compared with the standard protocol (median 1.06 mGy vs 0.56 mGy, p < 0.001). In both protocols, the left lens dose was significantly higher than the right (standard: 1.37 mGy vs 0.70 mGy, p < 0.001; reduction: 0.75 mGy vs 0.36 mGy, p < 0.001). No significant differences were observed in image noise or quality.</p><p><strong>Conclusion: </strong>The wedge filter significantly reduced the lens radiation dose during cerebral angiography without affecting image quality.</p><p><strong>Key points: </strong>Question The radiation dose to the eye lens during cerebral angiography remains unclear; a targeted method is needed to selectively reduce exposure to this radiosensitive organ. Findings This study directly measured eye lens radiation dose and found that using a wedge filter reduces exposure by nearly half while maintaining diagnostic image quality. Clinical relevance Using a wedge filter during routine neuroangiography effectively reduces eye lens radiation exposure with a simple operation, preserving image quality and potentially lowering the risk of radiation-induced cataracts.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"5996-6004"},"PeriodicalIF":4.7,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143963594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
European RadiologyPub Date : 2025-10-01Epub Date: 2025-04-12DOI: 10.1007/s00330-025-11519-y
Zhiqiang Bai, Lumin Xu, Zujun Ding, Yi Cao, Zepeng Wang, Wenjie Yang, Wei Xu, Hang Li
{"title":"Artificial intelligence in magnetic resonance imaging for predicting lymph node metastasis in rectal cancer patients: a meta-analysis.","authors":"Zhiqiang Bai, Lumin Xu, Zujun Ding, Yi Cao, Zepeng Wang, Wenjie Yang, Wei Xu, Hang Li","doi":"10.1007/s00330-025-11519-y","DOIUrl":"10.1007/s00330-025-11519-y","url":null,"abstract":"<p><strong>Objective: </strong>This meta-analysis aims to evaluate the diagnostic performance of magnetic resonance imaging (MRI)-based artificial intelligence (AI) in the preoperative detection of lymph node metastasis (LNM) in patients with rectal cancer and to compare it with the diagnostic performance of radiologists.</p><p><strong>Methods: </strong>A thorough literature search was conducted across PubMed, Embase, and Web of Science to identify relevant studies published up to September 2024. The selected studies focused on the diagnostic performance of MRI-based AI in detecting rectal cancer LNM. A bivariate random-effects model was employed to calculate pooled sensitivity and specificity, each reported with 95% confidence intervals (CIs). Study heterogeneity was assessed using the I<sup>2</sup> statistic. Furthermore, the modified quality assessment of diagnostic accuracy studies-2 (QUADAS-2) tool was applied to assess the methodological quality of the selected studies.</p><p><strong>Results: </strong>Seventeen studies were included in this meta-analysis. The pooled sensitivity, specificity, and area under the curve (AUC) for MRI-based AI in detecting preoperative LNM in rectal cancer were 0.71 (95% CI: 0.66-0.74), 0.71 (95% CI: 0.67-0.75), and 0.77 (95% CI: 0.73-0.80), respectively. For radiologists, these values were 0.64 (95% CI: 0.49-0.77), 0.72 (95% CI: 0.62-0.80), and 0.74 (95% CI: 0.68-0.80). Both analyses showed no significant publication bias (p > 0.05).</p><p><strong>Conclusions: </strong>MRI-based AI demonstrates diagnostic performance similar to that of radiologists. The high heterogeneity among studies limits the strength of these findings, and further research with external validation datasets is necessary to confirm the results and assess their practical clinical value.</p><p><strong>Key points: </strong>Question How effective is MRI-based AI in detecting LNM in rectal cancer patients compared to traditional radiology methods? Findings The diagnostic performance of MRI-based AI is comparable to radiologists, with pooled sensitivity and specificity both at 0.71, indicating moderate accuracy. Clinical relevance Integrating MRI-based AI can enhance diagnostic efficiency in identifying LNM, especially in settings with limited access to skilled radiologists, but requires further validation.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"6193-6206"},"PeriodicalIF":4.7,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143973764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
European RadiologyPub Date : 2025-10-01Epub Date: 2025-04-13DOI: 10.1007/s00330-025-11574-5
Meng Zhang, Chunchao Xia, Jing Tang, Li Yao, Na Hu, Jiaqi Li, Wanlin Peng, Sixian Hu, Zheng Ye, Xiaoyong Zhang, Jin Huang, Zhenlin Li
{"title":"Evaluation of high-resolution pituitary dynamic contrast-enhanced MRI using deep learning-based compressed sensing and super-resolution reconstruction.","authors":"Meng Zhang, Chunchao Xia, Jing Tang, Li Yao, Na Hu, Jiaqi Li, Wanlin Peng, Sixian Hu, Zheng Ye, Xiaoyong Zhang, Jin Huang, Zhenlin Li","doi":"10.1007/s00330-025-11574-5","DOIUrl":"10.1007/s00330-025-11574-5","url":null,"abstract":"<p><strong>Objective: </strong>This study aims to assess diagnostic performance of high-resolution dynamic contrast-enhanced (DCE) MRI with deep learning-based compressed sensing and super-resolution (DLCS-SR) reconstruction for identifying microadenomas.</p><p><strong>Materials and methods: </strong>This prospective study included 126 participants with suspected pituitary microadenomas who underwent DCE MRI between June 2023 and January 2024. Four image groups were derived from single-scan DCE MRI, which included 1.5-mm slice thickness images using DLCS-SR (1.5-mm DLCS-SR images), 1.5-mm slice thickness images with deep learning-based compressed sensing reconstruction (1.5-mm DLCS images), 1.5-mm routine images, and 3-mm slice thickness images using DLCS-SR (3-mm DLCS-SR images). Diagnostic criteria were established by incorporating laboratory findings, clinical symptoms, medical histories, previous imaging, and certain pathologic reports. Two readers assessed the diagnostic performance in identifying pituitary abnormalities and microadenomas. Diagnostic agreements were assessed using κ statistics, and intergroup comparisons for microadenoma detection were performed using the DeLong and McNemar tests.</p><p><strong>Results: </strong>The 1.5-mm DLCS-SR images (κ = 0.746-0.848) exhibited superior diagnostic agreement, outperforming 1.5-mm DLCS (κ = 0.585-0.687), 1.5-mm routine (κ = 0.449-0.487), and 3-mm DLCS-SR images (κ = 0.347-0.369) (p < 0.001 for all). Additionally, the performance of 1.5-mm DLCS-SR images in identifying microadenomas [area under the receiver operating characteristic curve (AUC), 0.89-0.94] surpassed that of 1.5-mm DLCS (AUC, 0.83-0.87; p = 0.042 and 0.011, respectively), 1.5-mm routine (AUC, 0.76-0.78; p < 0.001), and 3-mm DLCS-SR images (AUC, 0.72-0.74; p < 0.001).</p><p><strong>Conclusion: </strong>The findings revealed superior diagnostic performance of 1.5-mm DLCS-SR images in identifying pituitary abnormalities and microadenomas, indicating the clinical-potential of high-resolution DCE MRI.</p><p><strong>Key points: </strong>Question What strategies can overcome the resolution limitations of conventional dynamic contrast-enhanced (DCE) MRI, and which contribute to a high false-negative rate in diagnosing pituitary microadenomas? Findings Deep learning-based compressed sensing and super-resolution reconstruction applied to DCE MRI achieved high resolution while improving image quality and diagnostic efficacy. Clinical relevance DCE MRI with a 1.5-mm slice thickness and high in-plane resolution, utilizing deep learning-based compressed sensing and super-resolution reconstruction, significantly enhances diagnostic accuracy for pituitary abnormalities and microadenomas, enabling timely and effective patient management.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"5922-5934"},"PeriodicalIF":4.7,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143997815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"MR imaging and cholangiography show suboptimal performance for diagnosing ductal cholangiocarcinoma in primary sclerosing cholangitis patients.","authors":"Quentin Buhot, Quentin Bui, Hedi Chekir, Coline Delalandre, Sanaâ El Mouhadi, Quentin Vanderbecq, Mathilde Wagner, Lionel Arrivé","doi":"10.1007/s00330-025-11606-0","DOIUrl":"10.1007/s00330-025-11606-0","url":null,"abstract":"<p><strong>Objectives: </strong>Our purpose was to evaluate the performance of MR imaging/cholangiography for ductal cholangiocarcinoma (CCA) diagnosis and to search for specific MR features of ductal CCA among primary sclerosing cholangitis (PSC) patients.</p><p><strong>Methods: </strong>We retrospectively analyzed 31 patients from a single center, each with a diagnosis of PSC, and suspicion of ductal CCA. Ductal CCA had been suspected during multidisciplinary team meetings when high-grade biliary stenosis was associated with focal thickening of the biliary wall. Two radiologists blinded to clinical information and imaging history independently reviewed patients' MR examinations using a standardized model created for this study. Fisher's exact test and Student's t-test were used to analyze the population's characteristics. Fisher's exact test and the chi-square test were used to compare associations of categorical variables (each standard model's item) with the final diagnosis. Interobserver agreement was assessed by Cohen's κ coefficient.</p><p><strong>Results: </strong>Our population had a mean age of 42.7 ± 13.6 years and included 68% males. The final diagnosis was ductal CCA for 14 patients, and inflammatory stenosis for 17 patients. For diagnosing CCA, MR imaging/cholangiography exhibited a sensitivity of 43-50% and specificity of 70-76%, with low positive predictive (58-60%) and negative predictive (62-63%) values. Interobserver agreement ranged from κ = 0.04-0.75. Univariate analysis revealed no significant association between individual MR imaging/cholangiography features and CCA diagnosis.</p><p><strong>Conclusion: </strong>MR imaging/cholangiography showed suboptimal performance for ductal CCA diagnosis among PSC patients and we did not find any specific feature to distinguish ductal CCA from inflammatory stenosis.</p><p><strong>Key points: </strong>Question Diagnosing ductal cholangiocarcinoma in patients with primary sclerosing cholangitis remains challenging without known predictive MR imaging features. Findings MR imaging/cholangiography exhibited low sensitivity, specificity, and interobserver reliability for ductal cholangiocarcinoma diagnosis in primary sclerosing cholangitis and lacks reliability for distinguishing between benign and malignant strictures. Clinical relevance Diagnosing ductal cholangiocarcinoma in patients with primary sclerosing cholangitis remains challenging and our retrospective study demonstrates that MR imaging lacks reliability in distinguishing between benign and malignant high-grade strictures and did not find any specific MR feature of ductal CCA.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"6544-6553"},"PeriodicalIF":4.7,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143998403","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
European RadiologyPub Date : 2025-10-01Epub Date: 2025-04-07DOI: 10.1007/s00330-025-11554-9
Maria Ziegner, Johanna Pape, Martin Lacher, Annika Brandau, Tibor Kelety, Steffi Mayer, Franz Wolfgang Hirsch, Maciej Rosolowski, Daniel Gräfe
{"title":"Real-life benefit of artificial intelligence-based fracture detection in a pediatric emergency department.","authors":"Maria Ziegner, Johanna Pape, Martin Lacher, Annika Brandau, Tibor Kelety, Steffi Mayer, Franz Wolfgang Hirsch, Maciej Rosolowski, Daniel Gräfe","doi":"10.1007/s00330-025-11554-9","DOIUrl":"10.1007/s00330-025-11554-9","url":null,"abstract":"<p><strong>Objectives: </strong>This study aimed to evaluate the performance of an artificial intelligence (AI)-based software for fracture detection in pediatric patients within a real-life clinical setting. Specifically, it sought to assess (1) the stand-alone AI performance in real-life cohort and in selected set of medicolegal relevant fractures and (2) its influence on the diagnostic performance of inexperienced emergency room physicians.</p><p><strong>Materials and methods: </strong>The retrospective study involved 1672 radiographs of children under 18 years, obtained consecutively (real-life cohort) and selective (medicolegal cohort) in a tertiary pediatric emergency department. On these images, the stand-alone performance of a commercially available, deep learning-based software was determined. Additionally, three pediatric residents independently reviewed the radiographs before and after AI assistance, and the impact on their diagnostic accuracy was assessed.</p><p><strong>Results: </strong>In our cohort (median age 10.9 years, 59% male), the AI demonstrated a sensitivity of 92%, specificity of 83%, and accuracy of 87%. For medicolegally relevant fractures, the AI achieved a sensitivity of 100% for proximal tibia fractures, but only 68% for radial condyle fractures. AI assistance improved the residents' patient-wise sensitivity from 84 to 87%, specificity from 91 to 92%, and diagnostic accuracy from 88 to 90%. In 2% of cases, the readers, with the assistance of AI, erroneously discarded their correct diagnosis.</p><p><strong>Conclusion: </strong>The AI exhibited strong stand-alone performance in a pediatric setting and can modestly enhance the diagnostic accuracy of inexperienced physicians. However, the economic implications must be weighed against the potential benefits in patient safety.</p><p><strong>Key points: </strong>Question Does an artificial intelligence-based software for fracture detection influence inexperienced physicians in a real-life pediatric trauma population? Findings Addition of a well-performing artificial intelligence-based software led to a limited increase in diagnostic accuracy of inexperienced human readers. Clinical relevance Diagnosing fractures in children is especially challenging for less experienced physicians. High-performing artificial intelligence-based software as a \"second set of eyes,\" enhances diagnostic accuracy in a common pediatric emergency room setting.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"5881-5890"},"PeriodicalIF":4.7,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12417293/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143795043","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}